Recently, the development of foundational models with massive parameters has increasingly relied on distributed training frameworks, which require synchronization of parameter gradients across multiple GPUs, raising the demand for high-speed interconnects within GPU clusters. Although highbandwidth interconnect technologies like NVLink and InfiniBand support these distributed frameworks, they rely on wired media, leading to high cabling complexity and maintenance costs for large-scale data centers. To establish flexible and scalable data centers, Optical Wireless Communication (OWC) technology has emerged as a promising alternative to replace wired media. Most existing studies adopt the Fiber-Wireless-Fiber OWC (FWF-OWC) architecture, using custom-designed optical components for transceiver alignment and advanced techniques like wavelength division multiplexing (WDM) and high-order modulation to enhance communication rates. However, these systems are costly, require custom optical equipment, and have limited compatibility with optical modules. Additionally, current studies mainly conduct offline testing to measure physical-layer peak rates rather than real-time, end-to-end IP-level transmission rates, limiting practical applicability. To address these issues, we propose a minimalist FWF-OWC self-alignment system. This system performs alignment using a camera and a dualaxis stepper motor rotation platform, while being compatible with off-the-shelf SFP28 optical modules. Experimental results demonstrate that our system provides stable, plug-and-play IPlevel connectivity over a 2 -meter distance within a 10 -degree field of view, achieving TCP and UDP transmission rates of 24.2 Gbps and 25.0 Gbps, respectively. Additionally, our system also maintains an alignment tolerance of$\boldsymbol{\pm} \mathbf{0. 2}$degrees at a distance of 2 meters, highlighting the potential for further cost reduction in the alignment mechanism.

Direct alignment methods are increasingly used for aligning large language models (LLMs) with human preferences. However, these methods suffer from the issues of verbosity and likelihood displacement, which can be driven by the noisy preference pairs that induce similar likelihood for preferred and dispreferred responses. The contributions of this paper are two-fold. First, we propose a new preference alignment method based on zeroth-order, comparison-based optimization via comparison oracles and provide convergence guarantees for its basic scheme. Second, we improve our method using some heuristics and conduct the experiments to demonstrate the flexibility and compatibility of practical scheme in improving the performance of LLMs using noisy preference pairs. Evaluations are conducted across multiple base and instruction-tuned models (Mistral-7B, Llama-3-8B and Gemma-2-9B) with benchmarks (AlpacaEval 2, MT-Bench and Arena-Hard). Experimental results show the effectiveness of our method as an alternative to addressing the limitations of existing direct alignment methods. A highlight of our work is that we evidence the importance of designing specialized methods for preference pairs with distinct likelihood margin, which complements the recent findings in Razin et al (2025).

We provide a unified analysis of two-timescale gradient descent ascent (TTGDA) for solving structured nonconvex minimax optimization problems in the form of $\min_x \max_{y \in Y} f(x, y)$, where the objective function $f(x, y)$ is nonconvex in $x$ and concave in $y$, and the constraint set $Y \subseteq \mathbb{R}^n$ is convex and bounded. In the convex-concave setting, the single-timescale gradient descent ascent (GDA) algorithm is widely used in applications and has been shown to have strong convergence guarantees. In more general settings, however, it can fail to converge. Our contribution is to design TTGDA algorithms that are effective beyond the convex-concave setting, efficiently finding a stationary point of the function $\Phi(\cdot) := \max_{y \in Y} f(\cdot, y)$. We also establish theoretical bounds on the complexity of solving both smooth and nonsmooth nonconvex-concave minimax optimization problems. To the best of our knowledge, this is the first systematic analysis of TTGDA for nonconvex minimax optimization, shedding light on its superior performance in training generative adversarial networks (GANs) and in other real-world application problems.

Kernel-based optimal transport (OT) estimators offer an alternative, functional estimation procedure to address OT problems from samples. Recent works suggest that these estimators are more statistically efficient than plug-in (linear programming-based) OT estimators when comparing probability measures in high-dimensions (Vacher et al., 2021). Unfortunately,that statistical benefit comes at a very steep computational price: because their computation relies on the short-step interior-point method (SSIPM), which comes with a large iteration count in practice, these estimators quickly become intractable w.r.t. sample size $n$. To scale these estimators to larger $n$, we propose a nonsmooth fixedpoint model for the kernel-based OT problem, and show that it can be efficiently solved via a specialized semismooth Newton (SSN) method: We show, exploring the problem’s structure, that the per-iteration cost of performing one SSN step can be significantly reduced in practice. We prove that our SSN method achieves a global convergence rate of $O(1/\sqrt{k})$, and a local quadratic convergence rate under standard regularity conditions. We show substantial speedups over SSIPM on both synthetic and real datasets.

We study the complexity of optimizing nonsmooth nonconvex Lipschitz functions by producing $(\delta,\epsilon)$-Goldstein stationary points. Several recent works have presented randomized algorithms that produce such points using $\widetilde{O}(\delta^{-1}\epsilon^{-3})$ first-order oracle calls, independent of the dimension $d$. It has been an open problem as to whether a similar result can be obtained via a deterministic algorithm. We resolve this open problem, showing that randomization is necessary to obtain a dimension-free rate. In particular, we prove a lower bound of $\Omega(d)$ for any deterministic algorithm. Moreover, we show that unlike smooth or convex optimization, access to function values is required for any deterministic algorithm to halt within any finite time horizon.On the other hand, we prove that if the function is even slightly smooth, then the dimension-free rate of $\widetilde{O}(\delta^{-1}\epsilon^{-3})$ can be obtained by a deterministic algorithm with merely a logarithmic dependence on the smoothness parameter. Motivated by these findings, we turn to study the complexity of deterministically smoothing Lipschitz functions. Though there are well-known efficient black-box randomized smoothings, we start by showing that no such deterministic procedure can smooth functions in a meaningful manner (suitably defined), resolving an open question in the literature. We then bypass this impossibility result for the structured case of ReLU neural networks. To that end, in a practical “white-box” setting in which the optimizer is granted access to the network’s architecture, we propose a simple, dimension-free, deterministic smoothing of ReLU networks that provably preserves $(\delta,\epsilon)$-Goldstein stationary points. Our method applies to a variety of architectures of arbitrary depth, including ResNets and ConvNets.Combined with our algorithm for slightly-smooth functions, this yields the first deterministic, dimension-free algorithm for optimizing ReLU networks, circumventing our lower bound.

With the rapid development of intelligent vehicles in recent years, in-vehicle heterogeneous networks (HetNets) incorporating base stations (BSs) and vehicle access points (VAPs) have been widely deployed to support the ever-emerging diverse vehicular applications. However, most of the existing works focused on the HetNets covering multiple vehicles and considered the needs of all in-vehicle users as a holistic entity to maximize the overall performance of networks, which inevitably deviates from the local in-vehicle HetNet quality that most users are concerned about. Additionally, improving the energy efficiency (EE) of mobile devices in vehicles to extend their battery life is another significant issue, which has not been well addressed. To address the above issues, an intelligent in-vehicle power control and spectrum allocation mechanism is proposed in this work to maximize the EE of devices in the cabin while satisfying their dynamic traffic demands. Since this optimization problem has a non-convex mixed integer programming form, which is difficult to solve with traditional optimization methods, we further transform the optimization problem into a Markov Decision Process (MDP) and utilize a Proximal Policy Optimization (PPO) algorithm combined with the vehicle's location and historical channel state information (CSI) to achieve optimization objectives. Simulation results validate that the proposed algorithm can satisfy the dynamic traffic requirements of devices with high EE. Further comparison with baselines highlights the robustness of the proposed scheme under different device quantities and ratios.

We consider the problem of computing an equilibrium in a class of nonlinear generalized Nash equilibrium problems (NGNEPs) in which the strategy sets for each player are defined by the equality and inequality constraints that may depend on the choices of rival players. While the asymptotic global convergence and local convergence rate of certain algorithms have been extensively investigated, the iteration complexity analysis is still in its infancy. This paper provides two first-order algorithms based on quadratic penalty method (QPM) and augmented Lagrangian method (ALM), respectively, with an accelerated mirror-prox algorithm as the solver in each inner loop. We show the nonasymptotic convergence rate for these algorithms. In particular, we establish the global convergence guarantee for solving monotone and strongly monotone NGNEPs and provide the complexity bounds expressed in terms of the number of gradient evaluations. Experimental results demonstrate the efficiency of our algorithms in practice.

The filtering-clustering models, including trend filtering and convex clustering, have become an important source of ideas and modeling tools in machine learning and related fields. The statistical guarantee of optimal solutions in these models has been extensively studied yet the investigations on the computational aspect have remained limited. In particular, practitioners often employ the first-order algorithms in real-world applications and are impressed by their superior performance regardless of ill-conditioned structures of difference operator matrices, thus leaving open the problem of understanding the convergence property of first-order algorithms. This paper settles this open problem and contributes to the broad interplay between statistics and optimization by identifying a global error bound condition, which is satisfied by a large class of dual filtering-clustering problems, and designing a class of generalized dual gradient ascent algorithm, which is optimal first-order algorithms in deterministic, finite-sum and online settings. Our results are new and help explain why the filtering-clustering models can be efficiently solved by first-order algorithms. We also provide the detailed convergence rate analysis for the proposed algorithms in different settings, shedding light on their potential to solve the filtering-clustering models efficiently. We also conduct experiments on real datasets and the numerical results demonstrate the effectiveness of our algorithms.

Distributionally robust supervised learning (DRSL) is emerging as a key paradigm for building reliable machine learning systems for real-world applications–reflecting the need for classifiers and predictive models that are robust to the distribution shifts that arise from phenomena such as selection bias or nonstationarity. Existing algorithms for solving Wasserstein DRSL— one of the most popular DRSL frameworks based around robustness to perturbations in the Wasserstein distance—have serious limitations that limit their use in large-scale problems—in particular they involve solving complex subproblems and they fail to make use of stochastic gradients. We revisit Wasserstein DRSL through the lens of min-max optimization and derive scalable and efficiently implementable stochastic extra-gradient algorithms which provably achieve faster convergence rates than existing approaches. We demonstrate their effectiveness on synthetic and real data when compared to existing DRSL approaches. Key to our results is the use of variance reduction and random reshuffling to accelerate stochastic min-max optimization, the analysis of which may be of independent interest.

Motivated by applications to online learning in sparse estimation and Bayesian optimization, we consider the problem of online unconstrained nonsubmodular minimization with delayed costs in both full information and bandit feedback settings. In contrast to previous works on online unconstrained submodular minimization, we focus on a class of nonsubmodular functions with special structure, and prove regret guarantees for several variants of the online and approximate online bandit gradient descent algorithms in static and delayed scenarios. We derive bounds for the agent’s regret in the full information and bandit feedback setting, even if the delay between choosing a decision and receiving the incurred cost is unbounded. Key to our approach is the notion of $(\alpha, \beta)$-regret and the extension of the generic convex relaxation model from \citet{El-2020-Optimal}, the analysis of which is of independent interest. We conduct and showcase several simulation studies to demonstrate the efficacy of our algorithms.

From optimal transport to robust dimensionality reduction, many machine learning applicationscan be cast into the min-max optimization problems over Riemannian manifolds. Though manymin-max algorithms have been analyzed in the Euclidean setting, it has been elusive how theseresults translate to the Riemannian case. Zhang et al. (2022) have recently identified that geodesic convexconcave Riemannian problems admit always Sion’s saddle point solutions. Immediately, an importantquestion that arises is if a performance gap between the Riemannian and the optimal Euclidean spaceconvex concave algorithms is necessary. Our work is the first to answer the question in the negative:We prove that the Riemannian corrected extragradient (RCEG) method achieves last-iterate at alinear convergence rate at the geodesically strongly convex concave case, matching the euclidean one.Our results also extend to the stochastic or non-smooth case where RCEG & Riemanian gradientascent descent (RGDA) achieve respectively near-optimal convergence rates up to factors dependingon curvature of the manifold. Finally, we empirically demonstrate the effectiveness of RCEG insolving robust PCA.

Nonsmooth nonconvex optimization problems broadly emerge in machine learning and business decision making, whereas two core challenges impede the development of efficient solution methods with finite-time convergence guarantee: the lack of computationally tractable optimality criterion and the lack of computationally powerful oracles. The contributions of this paper are two-fold. First, we establish the relationship between the celebrated Goldstein subdifferential~\citep{Goldstein-1977-Optimization} and uniform smoothing, thereby providing the basis and intuition for the design of gradient-free methods that guarantee the finite-time convergence to a set of Goldstein stationary points. Second, we propose the gradient-free method (GFM) and stochastic GFM for solving a class of nonsmooth nonconvex optimization problems and prove that both of them can return a $(\delta,\epsilon)$-Goldstein stationary point of a Lipschitz function $f$ at an expected convergence rate at $O(d^{3/2}\delta^{-1}\epsilon^{-4})$ where $d$ is the problem dimension. Two-phase versions of GFM and SGFM are also proposed and proven to achieve improved large-deviation results. Finally, we demonstrate the effectiveness of 2-SGFM on training ReLU neural networks with the \textsc{Minst} dataset.

In this paper, we consider an unconstrained optimization model where the objective is a sum of a large number of possibly nonconvex functions, though overall the objective is assumed to be smooth and convex. Our bid to solving such model uses the framework of cubic regularization of Newton's method. As well known, the crux in cubic regularization is its utilization of the Hessian information, which may be computationally expensive for large-scale problems. To tackle this, we resort to approximating the Hessian matrix via sub-sampling. In particular, we propose to compute an approximated Hessian matrix by either uniformly or non-uniformly sub-sampling the components of the objective. Based upon such sampling strategy, we develop accelerated adaptive cubic regularization approaches and provide theoretical guarantees on global iteration complexity of $\O(\epsilon^{-1/3})$ with high probability, which matches that of the original accelerated cubic regularization methods Jiang et al. (2020) using the full Hessian information. Interestingly, we also show that in the worst case scenario our algorithm still achieves an $O(\epsilon^{-5/6}\log(\epsilon^{-1}))$ iteration complexity bound. The proof techniques are new to our knowledge and can be of independent interets. Experimental results on the regularized logistic regression problems demonstrate a clear effect of acceleration on several real data sets.

We study the complexity of approximating the multimarginal optimal transport (MOT) distance, a generalization of the classical optimal transport distance, considered here between $m$ discrete probability distributions supported each on $n$ support points. First, we show that the standard linear programming (LP) representation of the MOT problem is not a minimum-cost flow problem when $m \geq 3$. This negative result implies that some combinatorial algorithms, e.g., network simplex method, are not suitable for approximating the MOT problem, while the worst-case complexity bound for the deterministic interior-point algorithm remains a quantity of $\tilde{\mathcal{O}}(n^{3m})$. We then propose two simple and deterministic algorithms for approximating the MOT problem. The first algorithm, which we refer to as multimarginal Sinkhorn algorithm, is a provably efficient multimarginal generalization of the Sinkhorn algorithm. We show that it achieves a complexity bound of $\tilde{\mathcal{O}}(m^3n^m\varepsilon^{-2})$ for a tolerance $\varepsilon \in (0, 1)$. This provides a first near-linear time complexity bound guarantee for approximating the MOT problem and matches the best known complexity bound for the Sinkhorn algorithm in the classical OT setting when $m = 2$. The second algorithm, which we refer to as accelerated multimarginal Sinkhorn algorithm, achieves the acceleration by incorporating an estimate sequence and the complexity bound is $\tilde{\mathcal{O}}(m^3n^{m+1/3}\varepsilon^{-4/3})$. This bound is better than that of the first algorithm in terms of $1/\varepsilon$, and accelerated alternating minimization algorithm (Tupitsa et al., 2020) in terms of $n$. Finally, we compare our new algorithms with the commercial LP solver Gurobi. Preliminary results on synthetic data and real images demonstrate the effectiveness and efficiency of our algorithms.

We present several new complexity results for the entropic regularized algorithms that approximately solve the optimal transport (OT) problem between two discrete probability measures with at most $n$ atoms. First, we improve the complexity bound of a greedy variant of Sinkhorn, known as Greenkhorn, from $\tilde{O}(n^2\varepsilon^{-3})$ to $\tilde{O}(n^2\varepsilon^{-2})$. Notably, our result can match the best known complexity bound of Sinkhorn and help clarify why Greenkhorn significantly outperforms Sinkhorn in practice in terms of row/column updates as observed by Altschuler et al. (2017). Second, we propose a new algorithm, which we refer to as APDAMD and which generalizes an adaptive primal-dual accelerated gradient descent (APDAGD) algorithm (Dvurechensky et al., 2018) with a prespecified mirror mapping $\phi$. We prove that APDAMD achieves the complexity bound of $\tilde{O}(n^2\sqrt{\delta}\varepsilon^{-1})$ in which $\delta>0$ stands for the regularity of $\phi$. In addition, we show by a counterexample that the complexity bound of $\tilde{O}(\min\{n^{9/4}\varepsilon^{-1}, n^2\varepsilon^{-2}\})$ proved for APDAGD before is invalid and give a refined complexity bound of $\tilde{O}(n^{5/2}\varepsilon^{-1})$. Further, we develop a deterministic accelerated variant of Sinkhorn via appeal to estimated sequence and prove the complexity bound of $\tilde{O}(n^{7/3}\varepsilon^{-4/3})$. As such, we see that accelerated variant of Sinkhorn outperforms Sinkhorn and Greenkhorn in terms of $1/\varepsilon$ and APDAGD and accelerated alternating minimization (AAM) (Guminov et al., 2021) in terms of $n$. Finally, we conduct the experiments on synthetic and real data and the numerical results show the efficiency of Greenkhorn, APDAMD and accelerated Sinkhorn in practice.

Optimal transport (OT) distances are increasingly used as loss functions for statistical inference, notably in the learning of generative models or supervised learning. Yet, the behavior of minimum Wasserstein estimators is poorly understood, notably in high-dimensional regimes or under model misspecification. In this work we adopt the viewpoint of projection robust (PR) OT, which seeks to maximize the OT cost between two measures by choosing a $k$-dimensional subspace onto which they can be projected. Our first contribution is to establish several fundamental statistical properties of PR Wasserstein distances, complementing and improving previous literature that has been restricted to one-dimensional and well-specified cases. Next, we propose the integral PR Wasserstein (IPRW) distance as an alternative to the PRW distance, by averaging rather than optimizing on subspaces. Our complexity bounds can help explain why both PRW and IPRW distances outperform Wasserstein distances empirically in high-dimensional inference tasks. Finally, we consider parametric inference using the PRW distance. We provide an asymptotic guarantee of two types of minimum PRW estimators and formulate a central limit theorem for max-sliced Wasserstein estimator under model misspecification. To enable our analysis on PRW with projection dimension larger than one, we devise a novel combination of variational analysis and statistical theory.

Wasserstein Generative Adversarial Networks (WGANs) provide a versatile class of models, which have attracted great attention in various applications. However, this framework has two main drawbacks: (i) Wasserstein-1 (or Earth-Mover) distance is restrictive such that WGANs cannot always fit data geometry well; (ii) It is difficult to achieve fast training of WGANs. In this paper, we propose a new class of Relaxed Wasserstein (RW) distances by generalizing Wasserstein-1 distance with Bregman cost functions. We show that RW distances achieve nice statistical properties while not sacrificing the computational tractability. Combined with the GANs framework, we develop Relaxed WGANs (RWGANs) which are not only statistically flexible but can be approximated efficiently using heuristic approaches. Experiments on real images demonstrate that the RWGAN with Kullback-Leibler (KL) cost function outperforms other competing approaches, e.g., WGANs, even with gradient penalty.

This paper resolves a longstanding open question pertaining to the design of near-optimal first-order algorithms for smooth and strongly-convex-strongly-concave minimax problems. Current state-of-the-art first-order algorithms find an approximate Nash equilibrium using $\tilde{O}(\kappa_x+\kappa_y)$ or $\tilde{O}(\text{min}\{\kappa_x\sqrt{\kappa_y}, \sqrt{\kappa_x}\kappa_y\})$ gradient evaluations, where $\kappa_x$ and $\kappa_y$ are the condition numbers for the strong-convexity and strong-concavity assumptions. A gap still remains between these results and the best existing lower bound $\tilde{\Omega}(\sqrt{\kappa_x\kappa_y})$. This paper presents the first algorithm with $\tilde{O}(\sqrt{\kappa_x\kappa_y})$ gradient complexity, matching the lower bound up to logarithmic factors. Our algorithm is designed based on an accelerated proximal point method and an accelerated solver for minimax proximal steps. It can be easily extended to the settings of strongly-convex-concave, convex-concave, nonconvex-strongly-concave, and nonconvex-concave functions. This paper also presents algorithms that match or outperform all existing methods in these settings in terms of gradient complexity, up to logarithmic factors.

We consider nonconvex-concave minimax problems, $\min_{\mathbf{x}} \max_{\mathbf{y} \in \mathcal{Y}} f(\mathbf{x}, \mathbf{y})$, where $f$ is nonconvex in $\mathbf{x}$ but concave in $\mathbf{y}$ and $\mathcal{Y}$ is a convex and bounded set. One of the most popular algorithms for solving this problem is the celebrated gradient descent ascent (GDA) algorithm, which has been widely used in machine learning, control theory and economics. Despite the extensive convergence results for the convex-concave setting, GDA with equal stepsize can converge to limit cycles or even diverge in a general setting. In this paper, we present the complexity results on two-time-scale GDA for solving nonconvex-concave minimax problems, showing that the algorithm can find a stationary point of the function $\Phi(\cdot) := \max_{\mathbf{y} \in \mathcal{Y}} f(\cdot, \mathbf{y})$ efficiently. To the best our knowledge, this is the first nonasymptotic analysis for two-time-scale GDA in this setting, shedding light on its superior practical performance in training generative adversarial networks (GANs) and other real applications.

In this paper, we consider multi-agent learning via online gradient descent in a class of games called $\lambda$-cocoercive games, a fairly broad class of games that admits many Nash equilibria and that properly includes unconstrained strongly monotone games. We characterize the finite-time last-iterate convergence rate for joint OGD learning on $\lambda$-cocoercive games; further, building on this result, we develop a fully adaptive OGD learning algorithm that does not require any knowledge of problem parameter (e.g. cocoercive constant $\lambda$) and show, via a novel double-stopping time technique, that this adaptive algorithm achieves same finite-time last-iterate convergence rate as non-adaptive counterpart. Subsequently, we extend OGD learning to the noisy gradient feedback case and establish last-iterate convergence results–first qualitative almost sure convergence, then quantitative finite-time convergence rates– all under non-decreasing step-sizes. To our knowledge, we provide the first set of results that fill in several gaps of the existing multi-agent online learning literature, where three aspects–finite-time convergence rates, non-decreasing step-sizes, and fully adaptive algorithms have been unexplored before.

Projection robust Wasserstein (PRW) distance, or Wasserstein projection pursuit (WPP), is a robust variant of the Wasserstein distance. Recent work suggests that this quantity is more robust than the standard Wasserstein distance, in particular when comparing probability measures in high-dimensions. However, it is ruled out for practical application because the optimization model is essentially non-convex and non-smooth which makes the computation intractable. Our contribution in this paper is to revisit the original motivation behind WPP/PRW, but take the hard route of showing that, despite its non-convexity and lack of nonsmoothness, and even despite some hardness results proved by~\citet{Niles-2019-Estimation} in a minimax sense, the original formulation for PRW/WPP \textit{can} be efficiently computed in practice using Riemannian optimization, yielding in relevant cases better behavior than its convex relaxation. More specifically, we provide three simple algorithms with solid theoretical guarantee on their complexity bound (one in the appendix), and demonstrate their effectiveness and efficiency by conducing extensive experiments on synthetic and real data. This paper provides a first step into a computational theory of the PRW distance and provides the links between optimal transport and Riemannian optimization.

We study the fixed-support Wasserstein barycenter problem (FS-WBP), which consists in computing the Wasserstein barycenter of $m$ discrete probability measures supported on a finite metric space of size $n$. We show first that the constraint matrix arising from the standard linear programming (LP) representation of the FS-WBP is \textit{not totally unimodular} when $m \geq 3$ and $n \geq 3$. This result resolves an open question pertaining to the relationship between the FS-WBP and the minimum-cost flow (MCF) problem since it proves that the FS-WBP in the standard LP form is not an MCF problem when $m \geq 3$ and $n \geq 3$. We also develop a provably fast \textit{deterministic} variant of the celebrated iterative Bregman projection (IBP) algorithm, named \textsc{FastIBP}, with a complexity bound of $\tilde{O}(mn^{7/3}\varepsilon^{-4/3})$, where $\varepsilon \in (0, 1)$ is the desired tolerance. This complexity bound is better than the best known complexity bound of $\tilde{O}(mn^2\varepsilon^{-2})$ for the IBP algorithm in terms of $\varepsilon$, and that of $\tilde{O}(mn^{5/2}\varepsilon^{-1})$ from accelerated alternating minimization algorithm or accelerated primal-dual adaptive gradient algorithm in terms of $n$. Finally, we conduct extensive experiments with both synthetic data and real images and demonstrate the favorable performance of the \textsc{FastIBP} algorithm in practice.

We provide theoretical analyses for two algorithms that solve the regularized optimal transport (OT) problem between two discrete probability measures with at most $n$ atoms. We show that a greedy variant of the classical Sinkhorn algorithm, known as the Greenkhorn algorithm, can be improved to $\bigOtil\left(n^2/\varepsilon^2\right)$, improving on the best known complexity bound of $\bigOtil\left(n^2/\varepsilon^3\right)$. This matches the best known complexity bound for the Sinkhorn algorithm and helps explain why the Greenkhorn algorithm outperforms the Sinkhorn algorithm in practice. Our proof technique is based on a primal-dual formulation and provide a tight upper bound for the dual solution, leading to a class of adaptive primal-dual accelerated mirror descent (APDAMD) algorithms. We prove that the complexity of these algorithms is $\bigOtil\left(n^2\sqrt{\gamma}/\varepsilon\right)$ in which $\gamma \in (0, n]$ refers to some constants in the Bregman divergence. Experimental results on synthetic and real datasets demonstrate the favorable performance of the Greenkhorn and APDAMD algorithms in practice.

Topic sparsity refers to the observation that individual documents usually focus on several salient topics instead of covering a wide variety of topics, and a real topic adopts a narrow range of terms instead of a wide coverage of the vocabulary. Understanding this topic sparsity is especially important for analyzing user-generated web content and social media, which are featured in the form of extremely short posts and discussions. As topic sparsity of individual documents in online social media increases, so does the difficulty of analyzing the online text sources using traditional methods. In this paper, we propose two novel neural models by providing sparse posterior distributions over topics based on the Gaussian sparsemax construction, enabling efficient training by stochastic backpropagation. We construct an inference network conditioned on the input data and infer the variational distribution with the relaxed Wasserstein (RW) divergence. Unlike existing works based on Gaussian softmax construction and Kullback-Leibler (KL) divergence, our approaches can identify latent topic sparsity with training stability, predictive performance, and topic coherence. Experiments on different genres of large text corpora have demonstrated the effectiveness of our models as they outperform both probabilistic and neural methods.

With the soaring popularity of online social media like Twitter, analyzing short text has emerged as an increasingly important task which is challenging to classical topic models, as topic sparsity exists in short text. Topic sparsity refers to the observation that individual document usually concentrates on several salient topics, which may be rare in entire corpus. Understanding this sparse topical structure of short text has been recognized as the key ingredient for mining user-generated Web content and social medium, which are featured in the form of extremely short posts and discussions. However, the existing sparsity-enhanced topic models all assume over-complicated generative process, which severely limits their scalability and makes them unable to automatically infer the number of topics from data.

We consider a wide spectrum of regularized stochastic minimization problems, where the regularization term is composite with a linear function. Examples of this formulation include graph-guided regularized minimization, generalized Lasso and a class of ℓ1 regularized problems. The computational challenge is that the closed-form solution of the proximal mapping associated with the regularization term is not available due to the imposed linear composition. Fortunately, the structure of the regularization term allows us to reformulate it as a new convex-concave saddle point problem which can be solved using the Primal-Dual Hybrid Gradient (PDHG) approach. However, this approach may be inefficient in realistic applications as computing the full gradient of the expected objective function could be very expensive when the number of input data samples is considerably large. To address this issue, we propose a Stochastic PDHG (SPDHG) algorithm with either uniformly or non-uniformly averaged iterates. Through uniformly averaged iterates, the SPDHG algorithm converges in expectation withrate for general convex objectives and O(log (t)/t) rate for strongly convex objectives, respectively. While with non-uniformly averaged iterates, the SPDHG algorithm is expected to converge with O(1/t) rate for strongly convex objectives. Numerical experiments on different genres of datasets demonstrate that our proposed algorithm outperforms other competing algorithms.

Most collaborative filtering (CF) algorithms only make use of the rating scores given by users for items. However, it is often the case that each rating score is associated with a piece of review text. Such review texts, which are capable of providing us valuable information to reveal the reasons why users give a certain rating, have not been exploited and they are usually ignored by most CF algorithms. Moreover, the underlying relationship buried in users and items has not been fully exploited. Items we would recommend can often be characterized into hidden groups (e.g. comedy, horror movie and action movie), and users can also be organized as hidden communities. We propose a new generative model to predict user's ratings on previously unrated items by considering review texts as well as hidden user communities and item groups relationship. Regarding the rating scores, traditional algorithms would not perform well on uncovering the community and group information of each user and each item since the user-item rating matrix is dyadic involving the mutual interactions between users and items. Instead, co-clustering, which is capable of conducting simultaneous clustering of two variables, is able to take advantage of such user-item relationships to better predict the rating scores. Additionally, co-clustering would be more effective for modeling the generation of review texts since different user communities would discuss different topics and vary their own wordings or expression patterns when dealing with different item groups. Besides, by modeling as a mixed membership over community and group respectively, each user or item can belong to multiple communities or groups with varying degrees. We have conducted extensive experiments to predict the missing rating scores on 22 real word datasets. The experimental results demonstrate the superior performance of our proposed model comparing with the state-of-the-art methods.

We investigate latent aspect mining problem that aims at automatically discovering aspect information from a collection of review texts in a domain in an unsupervised manner. One goal is to discover a set of aspects which are previously unknown for the domain, and predict the user's ratings on each aspect for each review. Another goal is to detect key terms for each aspect. Existing works on predicting aspect ratings fail to handle the aspect sparsity problem in the review texts leading to unreliable prediction. We propose a new generative model to tackle the latent aspect mining problem in an unsupervised manner. By considering the user and item side information of review texts, we introduce two latent variables, namely, user intrinsic aspect interest and item intrinsic aspect quality facilitating better modeling of aspect generation leading to improvement on the accuracy and reliability of predicted aspect ratings. Furthermore, we provide an analytical investigation on the Maximum A Posterior (MAP) optimization problem used in our proposed model and develop a new block coordinate gradient descent algorithm to efficiently solve the optimization with closed-form updating formulas. We also study its convergence analysis. Experimental results on the two real-world product review corpora demonstrate that our proposed model outperforms existing state-of-the-art models.

Topic modeling has been proved to be an effective method for exploratory text mining. It is a common assumption of most topic models that a document is generated from a mixture of topics. In real-world scenarios, individual documents usually concentrate on several salient topics instead of covering a wide variety of topics. A real topic also adopts a narrow range of terms instead of a wide coverage of the vocabulary. Understanding this sparsity of information is especially important for analyzing user-generated Web content and social media, which are featured as extremely short posts and condensed discussions. In this paper, we propose a dual-sparse topic model that addresses the sparsity in both the topic mixtures and the word usage. By applying a "Spike and Slab" prior to decouple the sparsity and smoothness of the document-topic and topic-word distributions, we allow individual documents to select a few focused topics and a topic to select focused terms, respectively. Experiments on different genres of large corpora demonstrate that the dual-sparse topic model outperforms both classical topic models and existing sparsity-enhanced topic models. This improvement is especially notable on collections of short documents.